Researchers have released a new hyperspectral image dataset specifically designed for benchmarking salient object detection models. This dataset comprises 60 hyperspectral images, each accompanied by ground-truth binary images and sRGB renderings, addressing limitations of previous models tested on general-purpose datasets. The data collection considered variations in object size, contrast, and position, with ground truths meticulously labeled. Performance evaluations using the Area Under Curve (AUC) metric were conducted on existing hyperspectral saliency detection models, and the dataset is publicly accessible via GitHub and Hugging Face. AI
IMPACT Provides a dedicated resource for advancing research in hyperspectral salient object detection.
RANK_REASON The item describes the release of a new dataset for research purposes, detailed in an arXiv paper. [lever_c_demoted from research: ic=1 ai=1.0]
- arXiv
- GitHub
- Hugging Face
- Hyperspectral Image Dataset for Benchmarking on Salient Object Detection
- Nevrez İmamoğlu
AI-generated summary · Google Gemini · from 1 sources. How we write summaries →